SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting
By: Di Wu , Liu Liu , Xueyu Yuan and more
Potential Business Impact:
Builds 3D models from just a few pictures.
Articulated objects are ubiquitous in daily environments, and their 3D reconstruction holds great significance across various fields. However, existing articulated object reconstruction methods typically require costly inputs such as multi-stage and multi-view observations. To address the limitations, we propose a category-agnostic articulated object reconstruction framework via planar Gaussian Splatting, which only uses sparse-view RGB images from a single state. Specifically, we first introduce a Gaussian information field to perceive the optimal sparse viewpoints from candidate camera poses. Then we compress 3D Gaussians into planar Gaussians to facilitate accurate estimation of normal and depth. The planar Gaussians are optimized in a coarse-to-fine manner through depth smooth regularization and few-shot diffusion. Moreover, we introduce a part segmentation probability for each Gaussian primitive and update them by back-projecting part segmentation masks of renderings. Extensive experimental results demonstrate that our method achieves higher-fidelity part-level surface reconstruction on both synthetic and real-world data than existing methods. Codes will be made publicly available.
Similar Papers
REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
CV and Pattern Recognition
Lets computers build 3D models of moving objects.
SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting
Graphics
Makes robots and games understand how things bend.
MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation
CV and Pattern Recognition
Makes 3D pictures from few photos faster.